© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8871
    Prev
    Next
    INDEX
    Explanations

    key, definition, 0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼ĢéĹ¨çº¢
    -0.06
    ãĤĴ缮æĮĩãģĻ
    -0.06
    ç®Ĺ
    -0.06
     Super
    -0.06
     strips
    -0.06
     meas
    -0.06
    .log
    -0.06
    odos
    -0.06
     edição
    -0.06
    log
    -0.06
    POSITIVE LOGITS
    åĪ¶å®ļåĩº
    0.08
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.08
    éĢīåıĸ
    0.08
     Bla
    0.08
    ieras
    0.08
    inheit
    0.07
    åıĸãĤĬ
    0.07
    backs
    0.07
    ursor
    0.07
    åıĺéĩı
    0.07
    Activations Density 0.003%

    No Known Activations